© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1799
    Prev
    Next
    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     candidate
    -0.57
     candidates
    -0.53
    ABETH
    -0.53
    candidate
    -0.52
     CANDIDATE
    -0.52
    "]}
    -0.48
    candidates
    -0.48
     candidats
    -0.47
    elementary
    -0.46
     candidatos
    -0.45
    POSITIVE LOGITS
    DebuggerStep
    0.70
    GEBURTSDATUM
    0.70
    UrlResolution
    0.68
    +#+#
    0.66
    ècie
    0.66
    featureID
    0.64
    LookAnd
    0.64
    hips
    0.63
     MotionEvent
    0.63
    DeleteBehavior
    0.63
    Activations Density 0.176%

    No Known Activations